Initial commit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.spm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,616 @@
+---
+library_name: transformers
+language:
+- de
+- en
+- es
+- fr
+- lt
+- lv
+- prg
+- pt
+- sgs
+
+tags:
+- translation
+- opus-mt-tc-bible
+
+license: apache-2.0
+model-index:
+- name: opus-mt-tc-bible-big-bat-deu_eng_fra_por_spa
+  results:
+  - task:
+      name: Translation lit-deu
+      type: translation
+      args: lit-deu
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: lit-deu
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 23.7
+       - name: chr-F
+         type: chrf
+         value: 0.53223
+  - task:
+      name: Translation lit-eng
+      type: translation
+      args: lit-eng
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: lit-eng
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 32.6
+       - name: chr-F
+         type: chrf
+         value: 0.59361
+  - task:
+      name: Translation lit-fra
+      type: translation
+      args: lit-fra
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: lit-fra
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 30.0
+       - name: chr-F
+         type: chrf
+         value: 0.56786
+  - task:
+      name: Translation lit-por
+      type: translation
+      args: lit-por
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: lit-por
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 28.2
+       - name: chr-F
+         type: chrf
+         value: 0.55393
+  - task:
+      name: Translation lit-spa
+      type: translation
+      args: lit-spa
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: lit-spa
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 20.9
+       - name: chr-F
+         type: chrf
+         value: 0.49041
+  - task:
+      name: Translation lav-deu
+      type: translation
+      args: lav-deu
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: lav deu devtest
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 23.8
+       - name: chr-F
+         type: chrf
+         value: 0.54001
+  - task:
+      name: Translation lav-fra
+      type: translation
+      args: lav-fra
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: lav fra devtest
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 29.4
+       - name: chr-F
+         type: chrf
+         value: 0.57002
+  - task:
+      name: Translation lav-por
+      type: translation
+      args: lav-por
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: lav por devtest
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 26.7
+       - name: chr-F
+         type: chrf
+         value: 0.55155
+  - task:
+      name: Translation lav-spa
+      type: translation
+      args: lav-spa
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: lav spa devtest
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 20.8
+       - name: chr-F
+         type: chrf
+         value: 0.49259
+  - task:
+      name: Translation lit-eng
+      type: translation
+      args: lit-eng
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: lit eng devtest
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 32.1
+       - name: chr-F
+         type: chrf
+         value: 0.59073
+  - task:
+      name: Translation lit-por
+      type: translation
+      args: lit-por
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: lit por devtest
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 27.8
+       - name: chr-F
+         type: chrf
+         value: 0.55106
+  - task:
+      name: Translation lav-deu
+      type: translation
+      args: lav-deu
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: lav-deu
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 18.5
+       - name: chr-F
+         type: chrf
+         value: 0.47317
+  - task:
+      name: Translation lav-eng
+      type: translation
+      args: lav-eng
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: lav-eng
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 19.7
+       - name: chr-F
+         type: chrf
+         value: 0.53734
+  - task:
+      name: Translation lav-fra
+      type: translation
+      args: lav-fra
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: lav-fra
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 19.6
+       - name: chr-F
+         type: chrf
+         value: 0.47843
+  - task:
+      name: Translation lav-por
+      type: translation
+      args: lav-por
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: lav-por
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 19.3
+       - name: chr-F
+         type: chrf
+         value: 0.47027
+  - task:
+      name: Translation lav-spa
+      type: translation
+      args: lav-spa
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: lav-spa
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 22.7
+       - name: chr-F
+         type: chrf
+         value: 0.49428
+  - task:
+      name: Translation lit-deu
+      type: translation
+      args: lit-deu
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: lit-deu
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 19.4
+       - name: chr-F
+         type: chrf
+         value: 0.50279
+  - task:
+      name: Translation lit-eng
+      type: translation
+      args: lit-eng
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: lit-eng
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 28.1
+       - name: chr-F
+         type: chrf
+         value: 0.56642
+  - task:
+      name: Translation lit-fra
+      type: translation
+      args: lit-fra
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: lit-fra
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 22.6
+       - name: chr-F
+         type: chrf
+         value: 0.51276
+  - task:
+      name: Translation lit-por
+      type: translation
+      args: lit-por
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: lit-por
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 22.6
+       - name: chr-F
+         type: chrf
+         value: 0.50864
+  - task:
+      name: Translation lit-spa
+      type: translation
+      args: lit-spa
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: lit-spa
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 25.9
+       - name: chr-F
+         type: chrf
+         value: 0.53105
+  - task:
+      name: Translation lav-eng
+      type: translation
+      args: lav-eng
+    dataset:
+      name: tatoeba-test-v2021-08-07
+      type: tatoeba_mt
+      args: lav-eng
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 21.5
+       - name: chr-F
+         type: chrf
+         value: 0.63015
+  - task:
+      name: Translation lit-deu
+      type: translation
+      args: lit-deu
+    dataset:
+      name: tatoeba-test-v2021-08-07
+      type: tatoeba_mt
+      args: lit-deu
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 47.5
+       - name: chr-F
+         type: chrf
+         value: 0.66527
+  - task:
+      name: Translation lit-eng
+      type: translation
+      args: lit-eng
+    dataset:
+      name: tatoeba-test-v2021-08-07
+      type: tatoeba_mt
+      args: lit-eng
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 58.9
+       - name: chr-F
+         type: chrf
+         value: 0.72975
+  - task:
+      name: Translation lit-spa
+      type: translation
+      args: lit-spa
+    dataset:
+      name: tatoeba-test-v2021-08-07
+      type: tatoeba_mt
+      args: lit-spa
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 49.9
+       - name: chr-F
+         type: chrf
+         value: 0.67956
+  - task:
+      name: Translation multi-multi
+      type: translation
+      args: multi-multi
+    dataset:
+      name: tatoeba-test-v2020-07-28-v2023-09-26
+      type: tatoeba_mt
+      args: multi-multi
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 55.5
+       - name: chr-F
+         type: chrf
+         value: 0.71003
+  - task:
+      name: Translation lav-eng
+      type: translation
+      args: lav-eng
+    dataset:
+      name: newstest2017
+      type: wmt-2017-news
+      args: lav-eng
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 22.0
+       - name: chr-F
+         type: chrf
+         value: 0.49729
+  - task:
+      name: Translation lit-eng
+      type: translation
+      args: lit-eng
+    dataset:
+      name: newstest2019
+      type: wmt-2019-news
+      args: lit-eng
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 31.2
+       - name: chr-F
+         type: chrf
+         value: 0.59971
+---
+# opus-mt-tc-bible-big-bat-deu_eng_fra_por_spa
+
+## Table of Contents
+- [Model Details](#model-details)
+- [Uses](#uses)
+- [Risks, Limitations and Biases](#risks-limitations-and-biases)
+- [How to Get Started With the Model](#how-to-get-started-with-the-model)
+- [Training](#training)
+- [Evaluation](#evaluation)
+- [Citation Information](#citation-information)
+- [Acknowledgements](#acknowledgements)
+
+## Model Details
+
+Neural machine translation model for translating from Baltic languages (bat) to unknown (deu+eng+fra+por+spa).
+
+This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
+**Model Description:**
+- **Developed by:** Language Technology Research Group at the University of Helsinki
+- **Model Type:** Translation (transformer-big)
+- **Release**: 2024-05-30
+- **License:** Apache-2.0
+- **Language(s):**  
+  - Source Language(s): lav lit prg sgs
+  - Target Language(s): deu eng fra por spa
+  - Valid Target Language Labels: >>deu<< >>eng<< >>fra<< >>por<< >>spa<< >>xxx<<
+- **Original Model**: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/bat-deu+eng+fra+por+spa/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip)
+- **Resources for more information:**
+  -  [OPUS-MT dashboard](https://opus.nlpl.eu/dashboard/index.php?pkg=opusmt&test=all&scoreslang=all&chart=standard&model=Tatoeba-MT-models/bat-deu%2Beng%2Bfra%2Bpor%2Bspa/opusTCv20230926max50%2Bbt%2Bjhubc_transformer-big_2024-05-30)
+  - [OPUS-MT-train GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
+  - [More information about MarianNMT models in the transformers library](https://huggingface.co/docs/transformers/model_doc/marian)
+  - [Tatoeba Translation Challenge](https://github.com/Helsinki-NLP/Tatoeba-Challenge/)
+  - [HPLT bilingual data v1 (as part of the Tatoeba Translation Challenge dataset)](https://hplt-project.org/datasets/v1)
+  - [A massively parallel Bible corpus](https://aclanthology.org/L14-1215/)
+
+This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>>deu<<`
+
+## Uses
+
+This model can be used for translation and text-to-text generation.
+
+## Risks, Limitations and Biases
+
+**CONTENT WARNING: Readers should be aware that the model is trained on various public data sets that may contain content that is disturbing, offensive, and can propagate historical and current stereotypes.**
+
+Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)).
+
+## How to Get Started With the Model
+
+A short example code:
+
+```python
+from transformers import MarianMTModel, MarianTokenizer
+
+src_text = [
+    ">>deu<< Replace this with text in an accepted source language.",
+    ">>spa<< This is the second sentence."
+]
+
+model_name = "pytorch-models/opus-mt-tc-bible-big-bat-deu_eng_fra_por_spa"
+tokenizer = MarianTokenizer.from_pretrained(model_name)
+model = MarianMTModel.from_pretrained(model_name)
+translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
+
+for t in translated:
+    print( tokenizer.decode(t, skip_special_tokens=True) )
+```
+
+You can also use OPUS-MT models with the transformers pipelines, for example:
+
+```python
+from transformers import pipeline
+pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-bible-big-bat-deu_eng_fra_por_spa")
+print(pipe(">>deu<< Replace this with text in an accepted source language."))
+```
+
+## Training
+
+- **Data**: opusTCv20230926max50+bt+jhubc ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
+- **Pre-processing**: SentencePiece (spm32k,spm32k)
+- **Model Type:**  transformer-big
+- **Original MarianNMT Model**: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/bat-deu+eng+fra+por+spa/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip)
+- **Training Scripts**: [GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
+
+## Evaluation
+
+* [Model scores at the OPUS-MT dashboard](https://opus.nlpl.eu/dashboard/index.php?pkg=opusmt&test=all&scoreslang=all&chart=standard&model=Tatoeba-MT-models/bat-deu%2Beng%2Bfra%2Bpor%2Bspa/opusTCv20230926max50%2Bbt%2Bjhubc_transformer-big_2024-05-30)
+* test set translations: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/bat-deu+eng+fra+por+spa/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.test.txt)
+* test set scores: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/bat-deu+eng+fra+por+spa/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.eval.txt)
+* benchmark results: [benchmark_results.txt](benchmark_results.txt)
+* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
+
+| langpair | testset | chr-F | BLEU  | #sent | #words |
+|----------|---------|-------|-------|-------|--------|
+| lav-eng | tatoeba-test-v2021-08-07 | 0.63015 | 21.5 | 1631 | 11213 |
+| lit-deu | tatoeba-test-v2021-08-07 | 0.66527 | 47.5 | 1115 | 8531 |
+| lit-eng | tatoeba-test-v2021-08-07 | 0.72975 | 58.9 | 2528 | 17855 |
+| lit-spa | tatoeba-test-v2021-08-07 | 0.67956 | 49.9 | 454 | 2751 |
+| lav-deu | flores101-devtest | 0.54001 | 23.8 | 1012 | 25094 |
+| lav-fra | flores101-devtest | 0.57002 | 29.4 | 1012 | 28343 |
+| lav-por | flores101-devtest | 0.55155 | 26.7 | 1012 | 26519 |
+| lav-spa | flores101-devtest | 0.49259 | 20.8 | 1012 | 29199 |
+| lit-eng | flores101-devtest | 0.59073 | 32.1 | 1012 | 24721 |
+| lit-por | flores101-devtest | 0.55106 | 27.8 | 1012 | 26519 |
+| lit-deu | flores200-devtest | 0.53223 | 23.7 | 1012 | 25094 |
+| lit-eng | flores200-devtest | 0.59361 | 32.6 | 1012 | 24721 |
+| lit-fra | flores200-devtest | 0.56786 | 30.0 | 1012 | 28343 |
+| lit-por | flores200-devtest | 0.55393 | 28.2 | 1012 | 26519 |
+| lit-spa | flores200-devtest | 0.49041 | 20.9 | 1012 | 29199 |
+| lav-eng | newstest2017 | 0.49729 | 22.0 | 2001 | 47511 |
+| lit-eng | newstest2019 | 0.59971 | 31.2 | 1000 | 25878 |
+| lav-deu | ntrex128 | 0.47317 | 18.5 | 1997 | 48761 |
+| lav-eng | ntrex128 | 0.53734 | 19.7 | 1997 | 47673 |
+| lav-fra | ntrex128 | 0.47843 | 19.6 | 1997 | 53481 |
+| lav-por | ntrex128 | 0.47027 | 19.3 | 1997 | 51631 |
+| lav-spa | ntrex128 | 0.49428 | 22.7 | 1997 | 54107 |
+| lit-deu | ntrex128 | 0.50279 | 19.4 | 1997 | 48761 |
+| lit-eng | ntrex128 | 0.56642 | 28.1 | 1997 | 47673 |
+| lit-fra | ntrex128 | 0.51276 | 22.6 | 1997 | 53481 |
+| lit-por | ntrex128 | 0.50864 | 22.6 | 1997 | 51631 |
+| lit-spa | ntrex128 | 0.53105 | 25.9 | 1997 | 54107 |
+
+## Citation Information
+
+* Publications: [Democratizing neural machine translation with OPUS-MT](https://doi.org/10.1007/s10579-023-09704-w) and [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
+
+```bibtex
+@article{tiedemann2023democratizing,
+  title={Democratizing neural machine translation with {OPUS-MT}},
+  author={Tiedemann, J{\"o}rg and Aulamo, Mikko and Bakshandaeva, Daria and Boggia, Michele and Gr{\"o}nroos, Stig-Arne and Nieminen, Tommi and Raganato, Alessandro and Scherrer, Yves and Vazquez, Raul and Virpioja, Sami},
+  journal={Language Resources and Evaluation},
+  number={58},
+  pages={713--755},
+  year={2023},
+  publisher={Springer Nature},
+  issn={1574-0218},
+  doi={10.1007/s10579-023-09704-w}
+}
+
+@inproceedings{tiedemann-thottingal-2020-opus,
+    title = "{OPUS}-{MT} {--} Building open translation services for the World",
+    author = {Tiedemann, J{\"o}rg  and Thottingal, Santhosh},
+    booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
+    month = nov,
+    year = "2020",
+    address = "Lisboa, Portugal",
+    publisher = "European Association for Machine Translation",
+    url = "https://aclanthology.org/2020.eamt-1.61",
+    pages = "479--480",
+}
+
+@inproceedings{tiedemann-2020-tatoeba,
+    title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
+    author = {Tiedemann, J{\"o}rg},
+    booktitle = "Proceedings of the Fifth Conference on Machine Translation",
+    month = nov,
+    year = "2020",
+    address = "Online",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2020.wmt-1.139",
+    pages = "1174--1182",
+}
+```
+
+## Acknowledgements
+
+The work is supported by the [HPLT project](https://hplt-project.org/), funded by the European Union’s Horizon Europe research and innovation programme under grant agreement No 101070350. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland, and the [EuroHPC supercomputer LUMI](https://www.lumi-supercomputer.eu/).
+
+## Model conversion info
+
+* transformers version: 4.45.1
+* OPUS-MT git hash: a0ea3b3
+* port time: Mon Oct  7 17:27:51 EEST 2024
+* port machine: LM0-400-22516.local

benchmark_results.txt

@@ -0,0 +1,31 @@
+multi-multi	tatoeba-test-v2020-07-28-v2023-09-26	0.71003	55.5	6367	44692
+lav-deu	flores101-devtest	0.54001	23.8	1012	25094
+lav-fra	flores101-devtest	0.57002	29.4	1012	28343
+lav-por	flores101-devtest	0.55155	26.7	1012	26519
+lav-spa	flores101-devtest	0.49259	20.8	1012	29199
+lit-eng	flores101-devtest	0.59073	32.1	1012	24721
+lit-por	flores101-devtest	0.55106	27.8	1012	26519
+lit-deu	flores200-devtest	0.53223	23.7	1012	25094
+lit-eng	flores200-devtest	0.59361	32.6	1012	24721
+lit-fra	flores200-devtest	0.56786	30.0	1012	28343
+lit-por	flores200-devtest	0.55393	28.2	1012	26519
+lit-spa	flores200-devtest	0.49041	20.9	1012	29199
+lav-eng	newstest2017	0.49729	22.0	2001	47511
+lit-eng	newstest2019	0.59971	31.2	1000	25878
+lav-deu	ntrex128	0.47317	18.5	1997	48761
+lav-eng	ntrex128	0.53734	19.7	1997	47673
+lav-fra	ntrex128	0.47843	19.6	1997	53481
+lav-por	ntrex128	0.47027	19.3	1997	51631
+lav-spa	ntrex128	0.49428	22.7	1997	54107
+lit-deu	ntrex128	0.50279	19.4	1997	48761
+lit-eng	ntrex128	0.56642	28.1	1997	47673
+lit-fra	ntrex128	0.51276	22.6	1997	53481
+lit-por	ntrex128	0.50864	22.6	1997	51631
+lit-spa	ntrex128	0.53105	25.9	1997	54107
+lit-eng	tatoeba-test-v2020-07-28	0.72798	58.7	2500	17688
+lit-eng	tatoeba-test-v2021-03-30	0.72790	58.7	5003	35368
+lit-spa	tatoeba-test-v2021-03-30	0.68382	49.9	457	2763
+lav-eng	tatoeba-test-v2021-08-07	0.63015	21.5	1631	11213
+lit-deu	tatoeba-test-v2021-08-07	0.66527	47.5	1115	8531
+lit-eng	tatoeba-test-v2021-08-07	0.72975	58.9	2528	17855
+lit-spa	tatoeba-test-v2021-08-07	0.67956	49.9	454	2751

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "pytorch-models/opus-mt-tc-bible-big-bat-deu_eng_fra_por_spa",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 59466,
+  "decoder_vocab_size": 59467,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 788,
+  "forced_eos_token_id": null,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": null,
+  "max_position_embeddings": 1024,
+  "model_type": "marian",
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 59466,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "use_cache": true,
+  "vocab_size": 59467
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "_from_model_config": true,
+  "bad_words_ids": [
+    [
+      59466
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 59466,
+  "eos_token_id": 788,
+  "forced_eos_token_id": 788,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 59466,
+  "transformers_version": "4.45.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b4667803a7a2836fb089a866617aa57d6a5a793e8ff97d4b5755850f24e914d
+size 949273820

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3525e5635298f9c67cf944e9ec615e51112397cf60e1b725425fb032d3f9095
+size 949325061

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c92f9062726b6d6b01ba134f6ddcf9fbe07c1343c251335bd0902a965479dd9
+size 834375

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f30006b2bbd5c46ca39b1ecb0cc9009163828293d2dd2a2ff06931a2aa312a2
+size 819232

tokenizer_config.json

@@ -0,0 +1 @@
+{"source_lang": "bat", "target_lang": "deu+eng+fra+por+spa", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "separate_vocabs": false, "special_tokens_map_file": null, "name_or_path": "marian-models/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30/bat-deu+eng+fra+por+spa", "tokenizer_class": "MarianTokenizer"}